© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12040
    Prev
    Next
    INDEX
    Explanations

    a wide range of technical and business terms

    oai_token-act-pair · gemini-2.0-flash

    Research, insurance, alcohol

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     uſed
    -0.25
    Nevermind
    -0.24
     gravid
    -0.24
     inſ
    -0.23
     mey
    -0.22
     [];
    -0.22
     whoſe
    -0.22
     purpoſe
    -0.22
     uſ
    -0.21
     theſe
    -0.21
    POSITIVE LOGITS
     déchir
    0.90
     genoux
    0.89
     télécharge
    0.89
    ViewFeatures
    0.86
     cérami
    0.85
     rayures
    0.84
     Controls
    0.84
     Courses
    0.84
     Plans
    0.84
     réfrig
    0.84
    Activations Density 6.994%

    No Known Activations